Result 1 to 20 of 20 total
A robust incremental learning method for non-stationary environments. (English)
Neurocomputing 74, No. 11, 1800-1808 (2011).
1
On the effectiveness of distributed learning on different class-probability distributions of data. (English)
Lozano, Jose A. (ed.) et al., Advances in artificial intelligence. 14th conference of the Spanish association for artificial intelligence, CAEPIA 2011, La Laguna, Spain, November 7‒11, 2011. Proceedings. Berlin: Springer (ISBN 978-3-642-25273-0/pbk). Lecture Notes in Computer Science 7023. Lecture Notes in Artificial Intelligence, 114-123 (2011).
2
On the effectiveness of distributed learning on different class-probability distributions of data (English)
CAEPIA, 114-123 (2011).
3
Dealing with "very large" datasets - an overview of a promising research line: distributed learning (English)
ICAART (1), 476-481 (2011).
4
Fault prognosis of mechanical components using on-line learning neural networks. (English)
Diamantaras, Konstantinos (ed.) et al., Artificial neural networks ‒ ICANN 2010. 20th international conference, Thessaloniki, Greece, September 15‒18, 2010. Proceedings, Part I. Berlin: Springer (ISBN 978-3-642-15818-6/pbk). Lecture Notes in Computer Science 6352, 60-66 (2010).
5
An incremental learning method for neural networks based on sensitivity analysis. (English)
Meseguer, Pedro (ed.) et al., Current topics in artificial intelligence. 13th conference of the Spanish association for artificial intelligence, CAEPIA 2009, Seville, Spain, November 9‒13, 2009. Selected papers. Berlin: Springer (ISBN 978-3-642-14263-5/pbk). Lecture Notes in Computer Science 5988. Lecture Notes in Artificial Intelligence, 42-50 (2010).
6
A new convex objective function for the supervised learning of single-layer neural networks. (English)
Pattern Recognition 43, No. 5, 1984-1992 (2010).
7
Fault prognosis of mechanical components using on-line learning neural networks (English)
ICANN (1), 60-66 (2010).
8
An incremental learning method for neural networks in adaptive environments (English)
IJCNN, 1-8 (2010).
9
A supervised learning method for neural networks based on sensitivity analysis with automatic regularization. (English)
Cabestany, Joan (ed.) et al., Bio-inspired systems: Computational and ambient intelligence. 10th international work-conference on artificial neural networks, IWANN 2009, Salamanca, Spain, June 10‒12, 2009. Proceedings. Part I. Berlin: Springer (ISBN 978-3-642-02477-1/pbk). Lecture Notes in Computer Science 5517, 157-164 (2009).
10
Functional networks (English)
Encyclopedia of Artificial Intelligence, 667-676 (2009).
11
An incremental learning method for neural networks based on sensitivity analysis (English)
CAEPIA, 42-50 (2009).
12
A supervised learning method for neural networks based on sensitivity analysis with automatic regularization (English)
IWANN (1), 157-164 (2009).
13
A regularized learning method for neural networks based on sensitivity analysis (English)
ESANN, 289-294 (2008).
14
A linear learning method for multilayer perceptrons using least-squares. (English)
Yin, Hujun (ed.) et al., Intelligent data engineering and automated learning ‒ IDEAL 2007. 8th international conference, Birmingham, UK, December 16‒19, 2007. Proceedings. Berlin: Springer (ISBN 978-3-540-77225-5/pbk). Lecture Notes in Computer Science 4881, 365-374 (2007).
15
An improved version of the wrapper feature selection method based on functional decomposition (English)
ICANN (2), 240-249 (2007).
16
A fast semi-linear backpropagation learning algorithm (English)
ICANN (1), 190-198 (2007).
17
Classification of computer intrusions using functional networks. A comparative study (English)
ESANN, 579-584 (2007).
18
A linear learning method for multilayer perceptrons using least-squares (English)
IDEAL, 365-374 (2007).
19
A novel local classification method using growing neural gas and proximal support vector machines (English)
IJCNN, 1607-1612 (2007).
20
Result 1 to 20 of 20 total
Start
Contact
Print
General Help
